arm64: tlbflush: Allow stride to be specified for __flush_tlb_range()

mainline inclusion
from mainline-4.20-rc1
commit: 67a902ac598dca056366a7342f401aa6f605072f
category: feature
feature: Reduce synchronous TLB invalidation on ARM64
bugzilla: NA
CVE: NA

--------------------------------------------------

When we are unmapping intermediate page-table entries or huge pages, we
don't need to issue a TLBI instruction for every PAGE_SIZE chunk in the
VA range being unmapped.

Allow the invalidation stride to be passed to __flush_tlb_range(), and
adjust our "just nuke the ASID" heuristic to take this into account.
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NHanjun Guo <guohanjun@huawei.com>
Reviewed-by: NXuefeng Wang <wxf.wang@hisilicon.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

arch/arm64/include/asm/tlb.h

@@ -53,7 +53,7 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 	 * the __(pte|pmd|pud)_free_tlb() functions, so last level
 	 * TLBI is sufficient here.
 	 */
-	__flush_tlb_range(&vma, tlb->start, tlb->end, true);
+	__flush_tlb_range(&vma, tlb->start, tlb->end, PAGE_SIZE, true);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,

arch/arm64/include/asm/tlbflush.h

@@ -149,25 +149,28 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
  * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
  * necessarily a performance improvement.
  */
-#define MAX_TLB_RANGE	(1024UL << PAGE_SHIFT)
+#define MAX_TLBI_OPS	1024UL
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
-				     bool last_level)
+				     unsigned long stride, bool last_level)
 {
 	unsigned long asid = ASID(vma->vm_mm);
 	unsigned long addr;
 
-	if ((end - start) > MAX_TLB_RANGE) {
+	if ((end - start) > (MAX_TLBI_OPS * stride)) {
 		flush_tlb_mm(vma->vm_mm);
 		return;
 	}
 
+	/* Convert the stride into units of 4k */
+	stride >>= 12;
+
 	start = __TLBI_VADDR(start, asid);
 	end = __TLBI_VADDR(end, asid);
 
 	dsb(ishst);
-	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
+	for (addr = start; addr < end; addr += stride) {
 		if (last_level) {
 			__tlbi(vale1is, addr);
 			__tlbi_user(vale1is, addr);
@@ -186,14 +189,14 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	 * We cannot use leaf-only invalidation here, since we may be invalidating
 	 * table entries as part of collapsing hugepages or moving page tables.
 	 */
-	__flush_tlb_range(vma, start, end, false);
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, false);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 
-	if ((end - start) > MAX_TLB_RANGE) {
+	if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) {
 		flush_tlb_all();
 		return;
 	}